{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:27:13Z","timestamp":1777130833446,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887761","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Mel-Spectrogram Inversion via Alternating Direction Method of Multipliers"],"prefix":"10.1109","author":[{"given":"Yoshiki","family":"Masuyama","sequence":"first","affiliation":[{"name":"Tokyo Metropolitan University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natsuki","family":"Ueno","sequence":"additional","affiliation":[{"name":"Kumamoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobutaka","family":"Ono","sequence":"additional","affiliation":[{"name":"Tokyo Metropolitan University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.04.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3088581"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2678166"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2019.107368"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701851"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2884026"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3051870"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC53105.2022.9914686"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097224"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682744"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034486"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3189275"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095396"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref17","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ping"},{"key":"ref18","article-title":"Fast-speech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ren"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2280"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413973"},{"key":"ref21","first-page":"233","article-title":"Mel spectrogram inversion with stable pitch","volume-title":"Proc. Int. Soc. Music Inf. Retr. Conf. (ISMIR)","author":"Giorgi"},{"key":"ref22","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Kumar"},{"key":"ref23","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Kong"},{"key":"ref24","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Lee"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/eusipco.2019.8902504"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248111"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1561\/9781601984616"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ac37fa"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1561\/2400000003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2225617"},{"key":"ref32","first-page":"1","article-title":"A nonconvex approach for phase retrieval: Reshaped wirtinger flow and incremental algorithms","volume":"18","author":"Zhang","year":"2017","journal-title":"J. Mach. Learn. Represent."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/16M1064064"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854796"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682348"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3031464"},{"key":"ref37","volume-title":"P.862.2: Wideband extension to Recommendation P.862 for the assessment of wideband telephone networks and speech codecs","year":"2007"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref39","article-title":"Foley sound synthesis at the dcase 2023 challenge","author":"Choi","year":"2023"},{"key":"ref40","first-page":"375","article-title":"Signal reconstruction from STFT magnitude: a state of the art","volume-title":"Int. Conf. Digit. Audio Effects (DAFx)","author":"Strumel"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446058"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887761.pdf?arnumber=10887761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:26Z","timestamp":1774416206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887761","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}